Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
L. Lamontagne and M. Marchand (Eds.): Canadian AI 2006, LNAI 4013, pp. 134 145, 2006. Springer-Verlag Berlin Heidelberg 2006
 

Summary: L. Lamontagne and M. Marchand (Eds.): Canadian AI 2006, LNAI 4013, pp. 134 145, 2006.
Springer-Verlag Berlin Heidelberg 2006
Intelligent Information Personalization Leveraging
Constraint Satisfaction and Association Rule Methods
Syed Sibte Raza Abidi and Yan Zeng
Faculty of Computer Science, Dalhousie University,
Halifax, B3H 1W5, Canada
{sraza, yzeng@cs.dal.ca}
Abstract. Recommender systems, using information personalization methods,
provide information that is relevant to a user-model. Current information
personalization methods do not take into account whether multiple documents
when recommended together present a factually consistent outlook. In the realm
of content-based filtering, in this paper, we investigate establishing the factual
consistency between the set of documents deemed relevant to a user. We
approach information personalization as a constraint satisfaction problem,
where we attempt to satisfy two constraints--i.e. user-model constraints to
determine the relevance of a document to a user and consistency constraints to
establish factual consistency of the overall personalized information. Our
information personalization framework involves: (a) an automatic constraint
acquisition method, based on association rule mining, to derive consistency

  

Source: Abidi, Syed Sibte Raza - Faculty of Computer Science, Dalhousie University

 

Collections: Computer Technologies and Information Sciences